results

This model is a fine-tuned version of facebook/bart-large-cnn on the None dataset. It achieves the following results on the evaluation set:

• Loss: 7.6783
• Rouge1: 22.6282
• Rouge2: 2.7613
• Rougel: 15.7792
• Gen Len: 66.1839

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 3
• mixed_precision_training: Native AMP
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Gen Len
7.8707	0.5754	500	7.7020	22.5587	2.5824	15.5739	64.7494
7.7352	1.1507	1000	7.4834	22.4958	2.3149	15.6863	69.8138
7.2829	1.7261	1500	6.9061	20.4987	2.3443	15.3680	98.8828
7.0328	2.3015	2000	6.9069	20.6740	2.2923	15.6237	108.1402
6.9828	2.8769	2500	6.8401	21.0086	2.2733	15.7925	106.2667

Framework versions

• PEFT 0.14.0
• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0